diff --git a/tools/benchmark_tool/openvino/tools/benchmark/parameters.py b/tools/benchmark_tool/openvino/tools/benchmark/parameters.py
index 9463cebe633..29ea79376d8 100644
--- a/tools/benchmark_tool/openvino/tools/benchmark/parameters.py
+++ b/tools/benchmark_tool/openvino/tools/benchmark/parameters.py
@@ -98,7 +98,7 @@ def parse_args():
                            'Also, using nstreams>1 is inherently throughput-oriented option, while for the best-latency '
                            'estimations the number of streams should be set to 1. '
                            'See samples README for more details.')
-    args.add_argument('--latency_percentile', type=int, required=False, default=50, choices=range(1,101),
+    args.add_argument('--latency_percentile', type=int, required=False, default=50,
                       help='Optional. Defines the percentile to be reported in latency metric. The valid range is [1, 100]. The default value is 50 (median).')
     args.add_argument('-nthreads', '--number_threads', type=int, required=False, default=None,
                       help='Number of threads to use for inference on the CPU, GNA '
@@ -159,4 +159,8 @@ def parse_args():
                            "Example: -imean data[255,255,255],info[255,255,255]\n")
     parsed_args = parser.parse_args()
 
+    if parsed_args.latency_percentile < 0 or parsed_args.latency_percentile > 100:
+        parser.print_help()
+        raise RuntimeError("The percentile value is incorrect. The applicable values range is [1, 100].")
+
     return parsed_args